Llama Guard models
4 Llama Guard models from Meta on Hugging Face, from 1.2B to 12.0B parameters, published by Meta in BF16, with a 10M-token context. The smallest official model, Llama-Guard-3-1B, needs about 3.3 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Part of the Llama series
Pick a size
One row per official Llama Guard size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Llama-Guard-3-1B | 1.5B | 3.3 GB | 1.7 GB | 0.8 GB | RTX 3070 | $0.088/hr | not published for this architecture |
| Llama-Guard-3-8B | 8.0B | 17.9 GB | 9.0 GB | 4.5 GB | RTX A5000 | $0.176/hr | not published for this architecture |
| Llama-Guard-4-12B | 12.0B | 26.8 GB | 13.4 GB | 6.7 GB | RTX A6000 | $0.363/hr | 6.0 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Llama-Guard-3-1B | 1.5B | BF16 | 3.3 GB | RTX 3070 | $0.088/hr |
| Llama-Guard-3-8B | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| Llama-Guard-4-12B | 12.0B | BF16 | 26.8 GB | RTX A6000 | $0.363/hr |
Fine-tunes and community models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Llama-Phishsense-1B | 1.2B | BF16 | 2.8 GB | RTX 3070 | $0.088/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.